{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7IYRJTX2XZ4QLEHTZKAOWTSGVO","short_pith_number":"pith:7IYRJTX2","schema_version":"1.0","canonical_sha256":"fa3114cefabe790590f3ca80eb4e46abaebc32e8e436e068c3ac28623df44690","source":{"kind":"arxiv","id":"2508.12680","version":1},"attestation_state":"computed","paper":{"title":"Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Eric P. Xing, Jie Feng, Kun Zhou, Shibo Hao, Yuheng Zha, Yujia Wu, Yushu Wang, Zhengzhong Liu, Zhiting Hu, Zhi Xu","submitted_at":"2025-08-18T07:24:33Z","abstract_excerpt":"Despite their success, current training pipelines for reasoning VLMs focus on a limited range of tasks, such as mathematical and logical reasoning. As a result, these models face difficulties in generalizing their reasoning capabilities to a wide range of domains, primarily due to the scarcity of readily available and verifiable reward data beyond these narrowly defined areas. Moreover, integrating data from multiple domains is challenging, as the compatibility between domain-specific datasets remains uncertain. To address these limitations, we build a comprehensive RL-ready visual reasoning d"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.12680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T07:24:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e98346931499ba8e45c0940ec4d1ba5baaa02840ec131cb57d429367868c83df","abstract_canon_sha256":"6c3bff1327c3f03ab03fde79629cb8c9bcbc84bb33cc1cced978572f6a4050b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:25.284287Z","signature_b64":"ggF9aidQPp6Ud40DxYP1wQbpptYkDXi6eIvhTyX1SoyhkoK9CY/itMm/uSY5cXaXIqWY0xzN9xzvYwLhvT6VCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa3114cefabe790590f3ca80eb4e46abaebc32e8e436e068c3ac28623df44690","last_reissued_at":"2026-07-05T11:55:25.283829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:25.283829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Eric P. Xing, Jie Feng, Kun Zhou, Shibo Hao, Yuheng Zha, Yujia Wu, Yushu Wang, Zhengzhong Liu, Zhiting Hu, Zhi Xu","submitted_at":"2025-08-18T07:24:33Z","abstract_excerpt":"Despite their success, current training pipelines for reasoning VLMs focus on a limited range of tasks, such as mathematical and logical reasoning. As a result, these models face difficulties in generalizing their reasoning capabilities to a wide range of domains, primarily due to the scarcity of readily available and verifiable reward data beyond these narrowly defined areas. Moreover, integrating data from multiple domains is challenging, as the compatibility between domain-specific datasets remains uncertain. To address these limitations, we build a comprehensive RL-ready visual reasoning d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12680","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.12680/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.12680","created_at":"2026-07-05T11:55:25.283885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12680v1","created_at":"2026-07-05T11:55:25.283885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12680","created_at":"2026-07-05T11:55:25.283885+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IYRJTX2XZ4Q","created_at":"2026-07-05T11:55:25.283885+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IYRJTX2XZ4QLEHT","created_at":"2026-07-05T11:55:25.283885+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IYRJTX2","created_at":"2026-07-05T11:55:25.283885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22192","citing_title":"CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06121","citing_title":"Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20806","citing_title":"OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08539","citing_title":"OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO","json":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO.json","graph_json":"https://pith.science/api/pith-number/7IYRJTX2XZ4QLEHTZKAOWTSGVO/graph.json","events_json":"https://pith.science/api/pith-number/7IYRJTX2XZ4QLEHTZKAOWTSGVO/events.json","paper":"https://pith.science/paper/7IYRJTX2"},"agent_actions":{"view_html":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO","download_json":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO.json","view_paper":"https://pith.science/paper/7IYRJTX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12680&json=true","fetch_graph":"https://pith.science/api/pith-number/7IYRJTX2XZ4QLEHTZKAOWTSGVO/graph.json","fetch_events":"https://pith.science/api/pith-number/7IYRJTX2XZ4QLEHTZKAOWTSGVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO/action/storage_attestation","attest_author":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO/action/author_attestation","sign_citation":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO/action/citation_signature","submit_replication":"https://pith.science/pith/7IYRJTX2XZ4QLEHTZKAOWTSGVO/action/replication_record"}},"created_at":"2026-07-05T11:55:25.283885+00:00","updated_at":"2026-07-05T11:55:25.283885+00:00"}